In this paper, the parameter identification of bilinear state-space model (SSM) in the presence of random outliers and time-varying delays is investigated. Under the basis of the observable canonical form of the bilin...
详细信息
In this paper, the parameter identification of bilinear state-space model (SSM) in the presence of random outliers and time-varying delays is investigated. Under the basis of the observable canonical form of the bilinear model, the system output can be written as a regressive form, and a bilinear state observer is applied to estimate the unknown states. To eliminate the influence of outliers and time-varying delays on parameter estimation, we employ the Student's t$$ t $$ distribution to deal with the measurement noise and use a first-order Markov chain to model the delays. In the framework of expectation-maximization (EM) algorithm, the unknown parameters, delays, noise variance, states and transition probability matrix can be estimated iteratively. A numerical simulation and a continuous stirred tank reactor (CSTR) process demonstrate that the proposed algorithm has good immunity against outliers and time-varying delays and offers good estimation accuracy for the bilinear SSM.
This article addresses adaptive radar detection of N pulses coherently backscattered by a prospective target in heterogeneous disturbance. As customary K >= N range cells adjacent to the one under test are used for...
详细信息
This article addresses adaptive radar detection of N pulses coherently backscattered by a prospective target in heterogeneous disturbance. As customary K >= N range cells adjacent to the one under test are used for estimation purposes. The disturbance in each range cell is described by a non-Gaussian model based on a mixture of L < K Gaussian distributions. Gaussian components are characterized by an unknown low-rank matrix plus thermal noise with unknown power level. We first derive a detector inspired by the generalized likelihood ratio test that adaptively estimates the statistical properties of the disturbance from the observed data. To overcome the intractability of the involved maximum-likelihood estimation problem, a suitable approximate strategy based on the expectation-maximization algorithm is developed. This also allows us to classify the cell under test by selecting the "maximum a posteriori Gaussian distribution" for the disturbance (under both hypotheses). Accordingly, a likelihood ratio test is also proposed. An extensive performance analysis, conducted on synthetic data as well as on two different experimental datasets (PhaseOne and IPIX for land and sea radar returns, respectively), shows that the proposed approaches outperform state-of-the-art competitors in terms of both detection capabilities and false alarms control.
GNSS (Global Navigation Satellite Systems) tropospheric delay, specifically zenith wet delay (ZWD), shows clear spatial-temporal variations and is usually modeled as RWPN (random walk process noise). However, because ...
详细信息
GNSS (Global Navigation Satellite Systems) tropospheric delay, specifically zenith wet delay (ZWD), shows clear spatial-temporal variations and is usually modeled as RWPN (random walk process noise). However, because RWPN does not take the geographical position of GNSS stations and local weather conditions into account for precise point positioning (PPP), it may lead to biased ZWD estimates. To address the scientific problem and improve ZWD estimates, we adopt the expectation-maximization algorithm (EM algorithm) to validate the feasibility of estimating RWPN using only GNSS measurements. Numerical experiments reveal that using only GNSS observations is capable of determining the RWPN parameter, although it could take several days to reach a stable solution if the initial guess deviates far away from the truth. It is also shown that estimating RWPN can almost always effectively improve ZWD estimates by several millimeters in contrast with traditional PPP results. If the ambiguities are fixed to their integer values correctly, the accuracy of RWPN estimates for ZWD can be greatly reduced by 2mm/hour\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$2\text{ mm}/\sqrt{\text{hour}}$$\end{document}.
The present study proposes a novel dynamic mode decomposition (DMD) that can simultaneously estimate the reduced-order model, the original signal, and the system/observation noise model only from the noisy data. An ex...
详细信息
The present study proposes a novel dynamic mode decomposition (DMD) that can simultaneously estimate the reduced-order model, the original signal, and the system/observation noise model only from the noisy data. An expectation-maximization (EM)-algorithm DMD (EMDMD) combines DMD and the parameter adjustment of the linear dynamical system (LDS) based on the EM algorithm. The initial parameters based on the linearity of the reduced-order data are set by using DMD. Subsequently, the log-likelihood of the complete data is maximized by adjusting the LDS parameters while separating the noise. The proposed algorithm is applied to the benchmark data of the short-fat and tall-skinny data matrices with different noise and the time-series velocity fields of the flow around a circular cylinder and the separated flow around an airfoil. The performance of EMDMD in terms of system identification and noise separation from the noisy data is evaluated, and the EMDMD shows the highest system identification and noise separation performance in all data.
Because of inspection errors, expensive items such as computer chips are usually inspected more than once with the same testing device to further improve the quality of accepted items. Many researchers have considered...
详细信息
Because of inspection errors, expensive items such as computer chips are usually inspected more than once with the same testing device to further improve the quality of accepted items. Many researchers have considered various multiple inspection plans that minimize the expected total cost of inspection and misclassifications. We first propose a new Markovian inspection plan under which each item is tested repeatedly until we have a sufficient number of positive or negative test results. We then deal with the problem of estimating three model parameters: the type I and II errors of an automated test equipment and the fraction defective of incoming items. Because of computational difficulties in maximizing the likelihood of the three parameters, we propose the use of the expectation-maximization (EM) algorithm as an easy alternative. In a numerical analysis, we demonstrate the outstanding performance of our new inspection plan over previous ones.
Undeclared work (UW) is pervasive in economies. This explains the interest of public authorities in knowing its size and drivers. Unfortunately, this is a very complex task because several issues often arise in the co...
详细信息
Undeclared work (UW) is pervasive in economies. This explains the interest of public authorities in knowing its size and drivers. Unfortunately, this is a very complex task because several issues often arise in the collected data, due to the sensitivity of the topic. In sample surveys, one major problem is misclassification. Without appropriate adjustments, inference would provide biased estimates, the reason being the concealing of undeclared status. In order to overcome such problem, we developed a methodology based on a expectation-maximization algorithm that accounts for misclassification due to dishonest answering. Through the proposed approach, we are able to estimate the prevalence of UW and its determinants. The reliability of the methodology is validated through an extensive simulation study. An application to the Special Eurobarometer survey no. 402 on UW is provided.
Scene text detection is an important and challenging task in computer vision. For detecting arbitrarily-shaped texts, most existing methods require heavy data labeling efforts to produce polygon-level text region labe...
详细信息
Scene text detection is an important and challenging task in computer vision. For detecting arbitrarily-shaped texts, most existing methods require heavy data labeling efforts to produce polygon-level text region labels for supervised training. In order to reduce the cost in data labeling, we study mixed-supervised arbitrarily-shaped text detection by combining various weak supervision forms (e.g., image-level tags, coarse, loose and tight bounding boxes), which are far easier to annotate. Whereas the existing weakly-supervised learning methods (such as multiple instance learning) do not promote full object coverage, to approximate the performance of fully-supervised detection, we propose an expectation-maximization (EM) based mixed-supervised learning framework to train scene text detector using only a small amount of polygon-level annotated data combined with a large amount of weakly annotated data. The polygon-level labels are treated as latent variables and recovered from the weak labels by the EM algorithm. A new contour-based scene text detector is also proposed to facilitate the use of weak labels in our mixed-supervised learning framework. Extensive experiments on six scene text benchmarks show that (1) using only 10% strongly annotated data and 90% weakly annotated data, our method yields comparable performance to that of fully supervised methods, (2) with 100% strongly annotated data, our method achieves state-of-the-art performance on five scene text benchmarks (CTW1500, Total-Text, ICDAR-ArT, MSRA-TD500, and C-SVT), and competitive results on the ICDAR2015 Dataset. We will make our weakly annotated datasets publicly available.
An efficient initialization of the expectation-maximization algorithm to estimate mixture models via maximum likelihood is proposed. A fully unsupervised network-based initial-ization technique is provided by mapping ...
详细信息
An efficient initialization of the expectation-maximization algorithm to estimate mixture models via maximum likelihood is proposed. A fully unsupervised network-based initial-ization technique is provided by mapping time series to complex networks using as adja-cency matrix the Markov Transition Field associated to the time series. In this way, the optimal number of mixture model components and the vector of initial parameters can be directly obtained. An experiment conducted on financial times series with very different characteristics shows that our approach produces significantly better results if compared to conventional methods of initialization, such as K-means and Random, thus demonstrat-ing the effectiveness of the proposed method.(c) 2022 Elsevier Inc. All rights reserved.
A novel optimal time selection method for synthetic aperture radar (SAR) data processing via the expectation-maximization (EM) algorithm is proposed, which can reduce the computational complexity and improve the image...
详细信息
A novel optimal time selection method for synthetic aperture radar (SAR) data processing via the expectation-maximization (EM) algorithm is proposed, which can reduce the computational complexity and improve the image quality simultaneously. First, the Doppler frequency feature after the SAR processing is analyzed from the point of probability. Then, the Doppler frequency is modelled as the Gaussian mixture model (GMM), and the issue of optimal time selection can be implemented by the parameter estimation of GMM. The results of simulated and real measured data are given to demonstrate the effectiveness of the proposed method.
A Gaussian Mixture Model (GMM) is a parametric probability density function built as a weighted sum of Gaussian distributions. Gaussian mixtures are used for modelling the probability distribution in many fields of re...
详细信息
A Gaussian Mixture Model (GMM) is a parametric probability density function built as a weighted sum of Gaussian distributions. Gaussian mixtures are used for modelling the probability distribution in many fields of research nowadays. Nevertheless, in many real applications, the components are skewed or heavy tailed. For that reason, it is useful to model the mixtures as components with alpha-stable distribution. In this work, we present a mixture of skewed alpha-stable model where the parameters are estimated using the expectation-maximization algorithm. As the Gaussian distribution is a particular limiting case of alpha-stable distribution, the proposed model is a generalization of the widely used GMM. The proposed algorithm is much faster than the parameter estimation of the alpha-stable mixture model using a Bayesian approach and Markov chain Monte Carlo methods. Therefore, it is more suitable to be used for large vector observations. (C) 2020 Elsevier B.V. All rights reserved.
暂无评论